def main():
import sys
dbfile = sys.argv[1]
algor = sys.argv[2]
#dbfile = '../data/topicgj.db'
s,e = dbfile.rindex('/')+1, dbfile.rindex('.')
outfile = '../result/%s_orange_fmt.tab' % dbfile[s:e]
real_labels = cmpcluster.load_doc_labels(dbfile)
if not os.path.exists(outfile):
transfer_data_file(dbfile,outfile)
#os.system('emacs '+ outfile)
res_outfile = '../result/%s_cluster_result.txt' % algor
data = load_data_to_array(outfile)
if algor == 'kmeans':
kmeans_cluster_test(data, real_labels, res_outfile)
elif algor == 'tree':
tree_cluster_test(data, real_labels, res_outfile)
elif algor == 'som':
som_cluster_test(data, real_labels, res_outfile)
elif algor == 'dbscan':
dbscan_cluster_test(data,real_labels, res_outfile)
else:
raise NotImplementedError
os.system('emacs '+res_outfile)
def main():
import sys
dbfile = sys.argv[1]
algor = sys.argv[2]
#dbfile = '../data/topicgj.db'
s, e = dbfile.rindex('/') + 1, dbfile.rindex('.')
outfile = '../result/%s_orange_fmt.tab' % dbfile[s:e]
real_labels = cmpcluster.load_doc_labels(dbfile)
if not os.path.exists(outfile):
transfer_data_file(dbfile, outfile)
#os.system('emacs '+ outfile)
res_outfile = '../result/%s_cluster_result.txt' % algor
data = load_data_to_array(outfile)
if algor == 'kmeans':
kmeans_cluster_test(data, real_labels, res_outfile)
elif algor == 'tree':
tree_cluster_test(data, real_labels, res_outfile)
elif algor == 'som':
som_cluster_test(data, real_labels, res_outfile)
elif algor == 'dbscan':
dbscan_cluster_test(data, real_labels, res_outfile)
else:
raise NotImplementedError
os.system('emacs ' + res_outfile)
def classify(dbfile, run_num, log_info=None):
real = cmpcluster.load_doc_labels(dbfile)
print 'sample_test %d' % run_num
metrics = list()
cb = CommunityBuilder(dbfile, log_info)
for i in range(run_num):
predicted = cb.build()
metrics.append(cmp_cluster(predicted, real))
mean, std = mean_std(metrics)
return (mean, std)
def classify(dbfile, run_num, log_info=None):
real = cmpcluster.load_doc_labels(dbfile)
print 'sample_test %d' % run_num
metrics = list()
cb = CommunityBuilder(dbfile,log_info)
for i in range(run_num):
predicted = cb.build()
metrics.append(cmp_cluster(predicted,real))
mean,std = mean_std(metrics)
return (mean,std)
def main():
import pretext
import extract_keyword2
import worddf
dbfile = '../data/sougou.db'
logsteadyfile = '../result/sougou.log'
steadyfile = open(logsteadyfile,'w')
steadyfile.write(out_result_header())
if not os.path.exists(dbfile):
pretext.load_topiclist(dbfile,'/home/cs/download/cluster_data/sougou')
eva = WordWeightEvaluation(30,'../data/worddf')
ke = extract_keyword2.DBKeywordExtractor(dbfile,eva)
ke.init_db()
ke.content_keyword()
ke.title_keyword()
ke.topic_keyword()
ke.close_db()
cb = CommunityBuilder(dbfile)
metrics = list()
c = 1
real = cmpcluster.load_doc_labels(dbfile)
print 'fudan'
for i in range(c):
print 'Time %d' % (i+1)
predicted = cb.build(max_depth=5, min_doc_num=20)
metrics.append(cmp_cluster(predicted,real))
mean,std = mean_std(metrics)
meanstr = '%.1f \t%.3f \t%.3f \t%.3f \t%.3f\n' % tuple(mean)
stdstr = '%.1f \t%.3f \t%.3f \t%.3f \t%.3f\n' % tuple(std)
steadyfile.write(meanstr)
steadyfile.write(stdstr)
steadyfile.close()
os.system('emacs '+logsteadyfile)
def main():
import preproc_qqtopic
import extract_keyword2
import worddf
dbfile = '../data/steady_test.db'
logsteadyfile = '../result/steady_test.log'
steadyfile = open(logsteadyfile,'w')
steadyfile.write(out_result_header())
if not os.path.exists(dbfile):
preproc_qqtopic.load_topiclist(dbfile,'../data/topicgj')
ke = extract_keyword2.DBKeywordExtractor(dbfile)
ke.init_db()
ke.content_keyword()
ke.title_keyword()
ke.topic_keyword()
ke.close_db()
cb = CommunityBuilder(dbfile)
metrics = list()
c = 50
real = cmpcluster.load_doc_labels(dbfile)
print 'steady_test'
for i in range(c):
print 'Time %d' % (i+1)
predicted = cb.build()
metrics.append(cmp_cluster(predicted,real))
mean,std = mean_std(metrics)
meanstr = '%.1f \t%.3f \t%.3f \t%.3f \t%.3f\n' % tuple(mean)
stdstr = '%.1f \t%.3f \t%.3f \t%.3f \t%.3f\n' % tuple(std)
steadyfile.write(meanstr)
steadyfile.write(stdstr)
steadyfile.close()
os.system('emacs '+logsteadyfile)
def main():
import pretext
import extract_keyword2
import worddf
dbfile = '../data/sougou.db'
logsteadyfile = '../result/sougou.log'
steadyfile = open(logsteadyfile, 'w')
steadyfile.write(out_result_header())
if not os.path.exists(dbfile):
pretext.load_topiclist(dbfile, '/home/cs/download/cluster_data/sougou')
eva = WordWeightEvaluation(30, '../data/worddf')
ke = extract_keyword2.DBKeywordExtractor(dbfile, eva)
ke.init_db()
ke.content_keyword()
ke.title_keyword()
ke.topic_keyword()
ke.close_db()
cb = CommunityBuilder(dbfile)
metrics = list()
c = 1
real = cmpcluster.load_doc_labels(dbfile)
print 'fudan'
for i in range(c):
print 'Time %d' % (i + 1)
predicted = cb.build(max_depth=5, min_doc_num=20)
metrics.append(cmp_cluster(predicted, real))
mean, std = mean_std(metrics)
meanstr = '%.1f \t%.3f \t%.3f \t%.3f \t%.3f\n' % tuple(mean)
stdstr = '%.1f \t%.3f \t%.3f \t%.3f \t%.3f\n' % tuple(std)
steadyfile.write(meanstr)
steadyfile.write(stdstr)
steadyfile.close()
os.system('emacs ' + logsteadyfile)
def main():
import preproc_qqtopic
import extract_keyword2
import worddf
dbfile = '../data/steady_test.db'
logsteadyfile = '../result/steady_test.log'
steadyfile = open(logsteadyfile, 'w')
steadyfile.write(out_result_header())
if not os.path.exists(dbfile):
preproc_qqtopic.load_topiclist(dbfile, '../data/topicgj')
ke = extract_keyword2.DBKeywordExtractor(dbfile)
ke.init_db()
ke.content_keyword()
ke.title_keyword()
ke.topic_keyword()
ke.close_db()
cb = CommunityBuilder(dbfile)
metrics = list()
c = 50
real = cmpcluster.load_doc_labels(dbfile)
print 'steady_test'
for i in range(c):
print 'Time %d' % (i + 1)
predicted = cb.build()
metrics.append(cmp_cluster(predicted, real))
mean, std = mean_std(metrics)
meanstr = '%.1f \t%.3f \t%.3f \t%.3f \t%.3f\n' % tuple(mean)
stdstr = '%.1f \t%.3f \t%.3f \t%.3f \t%.3f\n' % tuple(std)
steadyfile.write(meanstr)
steadyfile.write(stdstr)
steadyfile.close()
os.system('emacs ' + logsteadyfile)
